anthropics/hh-rlhf
hh-rlhf
Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"
Builder
Anthropic
anthropics • ai-lab
Stars
1,839
Using upstream star count
Forks
159
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Apr 10, 2022
Project creation date
README Summary
> [!NOTE] > This github repo is now deprecated in favor of the HuggingFace hosted repository which contains the same data: https://huggingface.co/datasets/Anthropic/hh-rlhf
Community Evaluation
Loading…AI Dev Skills
Unmapped
AI Safety and AlignmentConstitutional AIDataset Curation and ManagementHuman-AI Interaction DesignHuman Preference LearningLanguage Model TrainingPreference ModelingReinforcement Learning from Human Feedback (RLHF)
Tags
AI Safety and AlignmentConstitutional AIDataset Curation and ManagementHuman-AI Interaction DesignHuman Preference LearningLanguage Model TrainingPreference ModelingReinforcement Learning from Human Feedback (RLHF)Anthropic / ClaudeForkedHuggingFaceLarge Language ModelsRed TeamingReinforcement LearningResearch / PapersRLHF
Taxonomy
Deployment Context
Modalities
Skill Areas
tag
Recent Activity
Updated 11 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
Evals & BenchmarkingPrimarySearch & KnowledgeFoundation ModelsModel TrainingLearning ResourcesSecurity & Safety
PM Skills
Safety & Alignment
Languages
No language breakdown recorded.
Timeline
- Project created
- Apr 10, 2022
- Forked
- Mar 14, 2026
- Your last push
- 11 months ago
- Upstream last push
- 11 months ago
- Tracked since
- Jun 17, 2025
Similar Repos
pgvector cosine similarity · $0
Loading…